阶段一通过了，但阶段二执行异常 "cross_attention_dim must be specified for CrossAttnDownBlock2D")

[a1123622944]

] 6s !CUDA_VISIBLE_DEVICES=0 torchrun --nnodes=1 --nproc_per_node=1 \ inference_stage2.py --config configs/stage2-hand.yaml --output data/hand_example/hand_chip/inpaint \ --ckpt checkpoint/stage2_hand/checkpoint-stage2-hand.ckpt /usr/local/lib/python3.10/dist-packages/diffusers/utils/outputs.py:63: FutureWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. torch.utils._pytree._register_pytree_node( /usr/local/lib/python3.10/dist-packages/diffusers/utils/outputs.py:63: FutureWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead. torch.utils._pytree._register_pytree_node( 09/30/2024 06:51:24 - INFO - root - Load scheduler, tokenizer and models. [rank0]: Traceback (most recent call last): [rank0]: File "/content/RealisHuman/inference_stage2.py", line 280, in [rank0]: main(launcher=args.launcher, sanity_check_during_validation=args.sanity_check_during_validation, [rank0]: File "/content/RealisHuman/inference_stage2.py", line 121, in main [rank0]: vae = AutoencoderKL.from_pretrained(pretrained_model_path, subfolder="vae") [rank0]: File "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn [rank0]: return fn(*args, kwargs) [rank0]: File "/usr/local/lib/python3.10/dist-packages/diffusers/models/modeling_utils.py", line 795, in from_pretrained [rank0]: model = cls.from_config(config, unused_kwargs) [rank0]: File "/usr/local/lib/python3.10/dist-packages/diffusers/configuration_utils.py", line 259, in from_config [rank0]: model = cls(init_dict) [rank0]: File "/usr/local/lib/python3.10/dist-packages/diffusers/configuration_utils.py", line 649, in inner_init [rank0]: init(self, *args, *init_kwargs) [rank0]: File "/usr/local/lib/python3.10/dist-packages/diffusers/models/autoencoders/autoencoder_kl.py", line 88, in init [rank0]: self.encoder = Encoder( [rank0]: File "/usr/local/lib/python3.10/dist-packages/diffusers/models/autoencoders/vae.py", line 103, in init [rank0]: down_block = get_down_block( [rank0]: File "/usr/local/lib/python3.10/dist-packages/diffusers/models/unet_2d_blocks.py", line 119, in get_down_block [rank0]: raise ValueError("cross_attention_dim must be specified for CrossAttnDownBlock2D") [rank0]: ValueError: cross_attention_dim must be specified for CrossAttnDownBlock2D E0930 06:51:25.450000 136206980706944 torch/distributed/elastic/multiprocessing/api.py:833] failed (exitcode: 1) local_rank: 0 (pid: 9788) of binary: /usr/bin/python3 Traceback (most recent call last): File "/usr/local/bin/torchrun", line 8, in sys.exit(main()) File "/usr/local/lib/python3.10/dist-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 348, in wrapper return f(args, kwargs) File "/usr/local/lib/python3.10/dist-packages/torch/distributed/run.py", line 901, in main run(args) File "/usr/local/lib/python3.10/dist-packages/torch/distributed/run.py", line 892, in run elastic_launch( File "/usr/local/lib/python3.10/dist-packages/torch/distributed/launcher/api.py", line 133, in call return launch_agent(self._config, self._entrypoint, list(args)) File "/usr/local/lib/python3.10/dist-packages/torch/distributed/launcher/api.py", line 264, in launch_agent raise ChildFailedError( torch.distributed.elastic.multiprocessing.errors.ChildFailedError:

[Wangbenzhi]

please refer the issue in diffuser. https://github.com/huggingface/diffusers/issues/5693